tune: slower, more gradual training for steady per-episode improvement 2c3dbb6 Aksh Parekh Claude Opus 4.6 commited on 5 days ago
style: increase all font sizes across dashboard for readability 0980a16 Aksh Parekh Claude Opus 4.6 commited on 5 days ago
feat: restart button + explanatory note on negative net reward d071454 Aksh Parekh Claude Opus 4.6 commited on 5 days ago
feat: dual-axis reward chart with cumulative net, dynamic mode label, and mean 0977416 Aksh Parekh Claude Opus 4.6 commited on 5 days ago
feat: incident-response reward system + live incident management dashboard 68d6c60 Aksh Parekh Claude Sonnet 4.6 commited on 5 days ago
feat: continuous PPO training + live web dashboard 71efc66 Aksh Parekh Claude Sonnet 4.6 commited on 5 days ago